The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review external source code files using the Read, Grep, and Glob tools. This process involves ingesting untrusted data (the code being reviewed) into the agent's context.
Ingestion points: External Kotlin/Compose source files read from the local file system via platform tools.
Boundary markers: The instructions do not explicitly define delimiters for separating the analyzed code from the agent's internal instructions.
Capability inventory: The skill is restricted to read-only tools (Read, Grep, Glob) and lacks capabilities for network access, file writing, or command execution.
Sanitization: No explicit sanitization or filtering of the input code is defined.
[EXTERNAL_DOWNLOADS]: The skill contains references to official documentation and guides hosted on developer.android.com and kotlinlang.org. These links point to well-known and trusted technology services and do not involve the execution of remote scripts or the download of untrusted binaries.

kotlin-ui-compose-multiplatform